Thank you for sending your enquiry! One of our team members will contact you shortly.
Thank you for sending your booking! One of our team members will contact you shortly.
Course Outline
Introduction to Multimodal LLMs in Vertex AI
- Overview of multimodal capabilities within Vertex AI
- Gemini models and the modalities they support
- Applications in enterprise and research environments
Configuring the Development Environment
- Setting up Vertex AI for multimodal workflow execution
- Managing datasets that span different modalities
- Practical lab: establishing the environment and preparing datasets
Long Context Windows and Advanced Reasoning
- Concepts behind long-context workflow management
- Applying long contexts to planning and decision-making processes
- Practical lab: executing long-context data analysis
Architecting Cross-Modal Workflows
- Integrating text, audio, and image analysis components
- Orchestrating sequential multimodal steps within pipelines
- Practical lab: constructing a cohesive multimodal pipeline
Managing Gemini API Parameters
- Configuring inputs and outputs for multimodal operations
- Enhancing inference speed and operational efficiency
- Practical lab: adjusting Gemini API settings for optimal performance
Advanced Applications and System Integration
- Developing interactive multimodal agents and assistants
- Connecting external APIs and third-party tools
- Practical lab: building a comprehensive multimodal application
Evaluation and Iterative Improvement
- Assessing the performance of multimodal systems
- Defining metrics for accuracy, alignment, and data drift
- Practical lab: conducting thorough evaluations of multimodal workflows
Summary and Future Directions
Requirements
- Strong proficiency in Python programming
- Hands-on experience in developing machine learning models
- Understanding of multimodal data types, including text, audio, and images
Target Audience
- AI researchers
- Senior-level developers
- Machine learning scientists
14 Hours
